Online Bayesian Recalibration of Brain–Computer Interfaces with Language Model Potentials

Brain–computer interfaces (BCIs) must continually adapt as neural signals drift, yet labeled calibration data is expensive to collect at time of use. Recent systems address this challenge by updating neural decoders using language-model–pseudo-labels, but they treat the pseudo-label as ground truth. We reinterpret recalibration as approximate Bayesian filtering: the decoder parameters are the latent states, and language models provide observations in the form of unnormalized potentials. Guided by this analysis, we introduce \textbf{B-CORP} (Bayesian Continual Online Recalibration with Pseudo-labels). B-CORP replaces hard pseudo-labels with a soft top-$K$ marginalization, increases the number of iterations in the coordinate ascent on the joint likelihood, and models parameter drift with a prior on latent dynamics. Across synthetic drifting regression tasks and real BCI benchmarks, including handwriting and speech BCI datasets, B-CORP attains word error rates consistently under 3\% on a difficult handwriting BCI dataset. B-CORP improves almost 30\% versus the state-of-the-art, while retaining performance even with poor pseudo-labels where naive methods fail. More broadly, our approach connects pseudo-label recalibration with online Bayesian inference, providing a principled foundation for problems requiring long-term recalibration with access to black box predictive models, such as LLMs, for use as strong priors over the labels.